Exploring surgical infection prediction: A comparative study of established risk indexes and a novel model

BACKGROUND

Surgical site infections are a major health problem that deteriorates the patients' health and increases health care costs. A reliable method to identify patients with modifiable risk of surgical site infection is necessary to reduce the incidence of them but data are limited. Hence the objective is to assess the predictive validity of a logistic regression model compared to risk indexes to identify patients at risk of surgical site infections.

METHODS

In this study, we evaluated the predictive validity of a new model which incorporates important predictors based on logistic regression model compared to three state-of-the-art risk indexes to identify high risk patients, recruited from 2016 to 2020 from a medium size hospital in North Norway, prone to surgical site infection.

RESULTS

The logistic regression model demonstrated significantly higher scores, defined as high-risk, in 110 patients with surgical site infections than in 110 patients without surgical site infections (p < 0.001, CI 19-44) compared to risk indexes. The logistic regression model achieved an area under the curve of 80 %, which was better than the risk indexes SSIRS (77 %), NNIS (59 %), and JSS-SSI (52 %) for predicting surgical site infections. The logistic regression model identified operating time and length of stay as the major predictors of surgical site infections.

CONCLUSIONS

The logistic regression model demonstrated better performance in predicting surgical site infections compared to three state-of-the-art risk indexes. The model could be further developed into a decision support tool, by incorporating predictors available prior to surgery, to identify patients with modifiable risk prone to surgical site infection.

Online shopping consumer perception analysis and future network security service technology using logistic regression model

In order to understand consumer perception, reduce risks in online shopping, and maintain online security, this study employs data envelopment analysis (DEA) to confirm the relationship between evaluation and stimuli. It establishes a model of stimuli-organism response and uses regression analysis to explore the relationships among negative online shopping evaluations, consumer perception of risk, and consumer behavior. This study employs attribution theory to analyze the impact of evaluations on consumer behavior and assesses the role of perceived risk as a mediator. The independent variable is negative comments, the dependent variable is consumer behavior, and logistic regression is used to empirically analyze the factors influencing online shopping security. The results indicate a positive correlation between the number of negative comments and consumers' delayed purchase behavior, with a correlation coefficient of 41%. The intensity of negative comments significantly impacts consumers' refusal to make a purchase, with a correlation coefficient of 38%. The length of negative comments substantially influences consumers' opposition to purchasing, also with a correlation coefficient of 38%. There is a close relationship between perceived risk and consumers' delayed shopping behavior and the number of negative comments, with 41% and 4% correlation coefficients, respectively. Perceived risk has a relatively smaller impact on consumers' opposition to purchase behavior, with a correlation coefficient of 27%. The length, intensity, and number of negative comments are correlated with consumers' opposition, refusal, and delayed consumption, negatively affecting consumer intent. Additionally, negative comments are related to perceived risk and consumer behavior. Perceived risk causally influences consumer behavior, while the convenience of shopping has a relatively minor impact on online shopping security. Factors like delivery speed, buyer reviews, brand, price, and consumer perception are significantly related to online shopping security. Consumer perception has the most significant impact on online shopping security, balancing secure and fast consumption under the guarantee of user experience. Strengthening consumer perception enhances consumers' ability to process risk information, helping them better identify risks and avoid using hazardous network software, tools, or technologies, thereby reducing potential online security risks.

A random forest algorithm-based prediction model for moderate to severe acute postoperative pain after orthopedic surgery under general anesthesia

BACKGROUND

Postoperative pain is one of the most common complications after surgery. In order to detect early and intervene in time for moderate to severe postoperative pain, it is necessary to identify risk factors and construct clinical prediction models. This study aimed to identify significant risk factors and establish a better-performing model to predict moderate to severe acute postoperative pain after orthopedic surgery under general anesthesia.

METHODS

Patients who underwent orthopedic surgery under general anesthesia were divided into patients with moderate to severe pain group (group P) and patients without moderate to severe pain group (group N) based on VAS scores. The features selected by Lasso regression were processed by the random forest and multivariate logistic regression models to predict pain outcomes. The classification performance of the two models was evaluated through the testing set. The area under the curves (AUC), the accuracy of the classifiers, and the classification error rate for both classifiers were calculated, the better-performing model was used to predict moderate to severe acute postoperative pain after orthopedic surgery under general anesthesia.

RESULTS

A total of 327 patients were enrolled in this study (228 in the training set and 99 in the testing set). The incidence of moderate to severe postoperative pain was 41.3%. The random forest model revealed a classification error rate of 25.2% and an AUC of 0.810 in the testing set. The multivariate logistic regression model revealed a classification error rate of 31.3% and an AUC of 0.764 in the testing set. The random forest model was chosen for predicting clinical outcomes in this study. The risk factors with the greatest and second contribution were immobilization and duration of surgery, respectively.

CONCLUSIONS

The random forest model can be used to predict moderate to severe acute postoperative pain after orthopedic surgery under general anesthesia, which is of potential clinical application value.

Analysis and prediction of older adult sports participation in South Korea using artificial neural networks and logistic regression models

BACKGROUND

Korea's aging population and the lack of older adult participation in sports are increasing medical expenses.

AIMS

This study aimed to segment older adult sports participants based on their demographic characteristics and exercise practice behavior and applied artificial neural network and logistic regression models to these segments to best predict the effect of medical cost reduction. It presents strategies for older adult sports participation.

METHODS

A sample comprising data on 1,770 older adults aged 50 years and above was drawn from the 2019 National Sports Survey. The data were analyzed through frequency analysis, hierarchical and K-means clustering, artificial neural network, logistic regression, cross-tabulation analyses, and one-way ANOVA using SPSS 23 and Modeler 14.2.

RESULTS

The participants were divided into five clusters. The artificial neural network and logistic analysis models showed that the cluster comprising married women in their 60s who participated in active exercise had the highest possibility of reducing medical expenses.

DISCUSSION

Targeting women in their 60s who actively participate in sports, the government should expand the supply of local gymnasiums, community centers, and sports programs. If local gymnasiums and community centers run sports programs and appoint appropriate sports instructors, the most effective medical cost reduction effect can be obtained.

CONCLUSIONS

This study contributes to the field by providing insights into the specific demographic segments to focus on for measures to reduce medical costs through sports participation.

Construction and validation of machine learning models for sepsis prediction in patients with acute pancreatitis

BACKGROUND

This study aimed to construct predictive models for the risk of sepsis in patients with Acute pancreatitis (AP) using machine learning methods and compared optimal one with the logistic regression (LR) model and scoring systems.

METHODS

In this retrospective cohort study, data were collected from the Medical Information Mart for Intensive Care III (MIMIC III) database between 2001 and 2012 and the MIMIC IV database between 2008 and 2019. Patients were randomly divided into training and test sets (8:2). The least absolute shrinkage and selection operator (LASSO) regression plus 5-fold cross-validation were used to screen and confirm the predictive factors. Based on the selected predictive factors, 6 machine learning models were constructed, including support vector machine (SVM), K-nearest neighbour (KNN), multi-layer perceptron (MLP), LR, gradient boosting decision tree (GBDT) and adaptive enhancement algorithm (AdaBoost). The models and scoring systems were evaluated and compared using sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and the area under the curve (AUC).

RESULTS

A total of 1, 672 patients were eligible for participation. In the training set, 261 AP patients (19.51%) were diagnosed with sepsis. The predictive factors for the risk of sepsis in AP patients included age, insurance, vasopressors, mechanical ventilation, Glasgow Coma Scale (GCS), heart rate, respiratory rate, temperature, SpO2, platelet, red blood cell distribution width (RDW), International Normalized Ratio (INR), and blood urea nitrogen (BUN). The AUC of the GBDT model for sepsis prediction in the AP patients in the testing set was 0.985. The GBDT model showed better performance in sepsis prediction than the LR, systemic inflammatory response syndrome (SIRS) score, bedside index for severity in acute pancreatitis (BISAP) score, sequential organ failure assessment (SOFA) score, quick-SOFA (qSOFA), and simplified acute physiology score II (SAPS II).

CONCLUSION

The present findings suggest that compared to the classical LR model and SOFA, qSOFA, SAPS II, SIRS, and BISAP scores, the machine learning model-GBDT model had a better performance in predicting sepsis in the AP patients, which is a useful tool for early identification of high-risk patients and timely clinical interventions.

Genetic interaction in the association between oxidative stress and diabetes in the Spanish population

Oxidative stress (OS) is a relevant intermediate mechanism involved in Type 2 Diabetes Mellitus (T2D) development. To date, the interaction between OS parameters and variations in genes related to T2D has not been analyzed.

AIMS

To study the genetic interaction of genes potentially related to OS levels (redox homeostasis, renin-angiotensin-aldosterone system, endoplasmic stress response, dyslipidemia, obesity and metal transport) and OS and T2D risk in a general population from Spain (the Hortega Study) in relation to the risk of suffering from T2D.

MATERIALS AND METHODS

One thousand five hundred and two adults from the University Hospital Rio Hortega area were studied and 900 single nucleotide polymorphisms (SNPs) from 272 candidate genes were analyzed.

RESULTS

There were no differences in OS levels between cases and controls. Some polymorphisms were associated with T2D and with OS levels. Significant interactions were observed between OS levels and two polymorphisms in relation to T2D presence: rs196904 (ERN1 gene) and rs2410718 (COX7C gene); and between OS levels and haplotypes of the genes: SP2, HFF1A, ILI8R1, EIF2AK2, TXNRD2, PPARA, NDUFS2 and ERN1.

CONCLUSIONS

Our results indicate that genetic variations of the studied genes are associated with OS levels and that their interaction with OS parameters may contribute to the risk of developing T2D in the Spanish general population. These data support the importance of analyzing the influence of OS levels and their interaction with genetic variations in order to establish their real impact in T2D risk. Further studies are required to identify the real relevance of interactions between genetic variations and OS levels and the mechanisms involved in them.

Development and application of hepatocellular carcinoma risk prediction model based on clinical characteristics and liver related indexes

BACKGROUND

Hepatocellular carcinoma (HCC) is difficult to diagnose with poor therapeutic effect, high recurrence rate and has a low survival rate. The survival of patients with HCC is closely related to the stage of diagnosis. At present, no specific serological indicator or method to predict HCC, early diagnosis of HCC remains a challenge, especially in China, where the situation is more severe.

AIM

To identify risk factors associated with HCC and establish a risk prediction model based on clinical characteristics and liver-related indicators.

METHODS

The clinical data of patients in the Affiliated Hospital of North Sichuan Medical College from 2016 to 2020 were collected, using a retrospective study method. The results of needle biopsy or surgical pathology were used as the grouping criteria for the experimental group and the control group in this study. Based on the time of admission, the cases were divided into training cohort (n = 1739) and validation cohort (n = 467). Using HCC as a dependent variable, the research indicators were incorporated into logistic univariate and multivariate analysis. An HCC risk prediction model, which was called NSMC-HCC model, was then established in training cohort and verified in validation cohort.

RESULTS

Logistic univariate analysis showed that, gender, age, alpha-fetoprotein, and protein induced by vitamin K absence or antagonist-II, gamma-glutamyl transferase, aspartate aminotransferase and hepatitis B surface antigen were risk factors for HCC, alanine aminotransferase, total bilirubin and total bile acid were protective factors for HCC. When the cut-off value of the NSMC-HCC model joint prediction was 0.22, the area under receiver operating characteristic curve (AUC) of NSMC-HCC model in HCC diagnosis was 0.960, with sensitivity 94.40% and specificity 95.35% in training cohort, and AUC was 0.966, with sensitivity 90.00% and specificity 94.20% in validation cohort. In early-stage HCC diagnosis, the AUC of NSMC-HCC model was 0.946, with sensitivity 85.93% and specificity 93.62% in training cohort, and AUC was 0.947, with sensitivity 89.10% and specificity 98.49% in validation cohort.

CONCLUSION

The newly NSMC-HCC model was an effective risk prediction model in HCC and early-stage HCC diagnosis.

Parsimonious clinical prediction model for the diagnosis of complicated appendicitis

Objective

To develop a logistic regression model that combines clinical and radiological parameters for prediction of complicated appendicitis.

Methods

248 patients with histologically proven uncomplicated (n = 214) and complicated (n = 34) acute appendicitis were analyzed retrospectively. All patients had undergone a presurgical abdominal and/or pelvic computed tomography (CT) scan, assessed by two radiologists. A model using univariate and multivariate logistic regression analyses was developed, and the strength of association between independent predictors and complicated acute appendicitis was evaluated by adjusted odds radio. Clinical parameters were gender, age, anorexia, vomiting, duration of symptoms, right lower abdominal quadrant (RLQ) tenderness, rebound tenderness, body temperature, white blood cell (WBC) count, and neutrophil ratio. Radiological parameters were appendix diameter, appendicolith, caecal wall thickening, mesenteric lymphadenopathy, extraluminal air, abscess, fat stranding, and periappendicular fluid.

Results

Four features (body temperature＞37.2 °C, vomiting, appendicolith, and periappendiceal fluid) were included in the logistic regression model, and yielded an area under the curve (AUC) of 0.87 (95% confidence interval (CI), 0.80-0.93), sensitive of 88%, and specificity of 74%.

Conclusion

The logistic regression model makes an accurate and simple prediction of complicated appendicitis possible.

[Risk predictive models of healthcare-seeking delay among imported malaria patients in Jiangsu Province based on the machine learning]

OBJECTIVE

To create risk predictive models of healthcare-seeking delay among imported malaria patients in Jiangsu Province based on machine learning algorithms, so as to provide insights into early identification of imported malaria cases in Jiangsu Province.

METHODS

Case investigation, first symptoms and time of initial diagnosis of imported malaria patients in Jiangsu Province in 2019 were captured from Infectious Disease Report Information Management System and Parasitic Disease Prevention and Control Information Management System of Chinese Center for Disease Control and Prevention. The risk predictive models of healthcare-seeking delay among imported malaria patients were created with the back propagation (BP) neural network model, logistic regression model, random forest model and Bayesian model using thirteen factors as independent variables, including occupation, species of malaria parasite, main clinical manifestations, presence of complications, severity of disease, age, duration of residing abroad, frequency of malaria parasite infections abroad, incubation period, level of institution at initial diagnosis, country of origin, number of individuals travelling with patients and way to go abroad, and time of healthcare-seeking delay as a dependent variable. Logistic regression model was visualized using a nomogram, and the nomogram was evaluated using calibration curves. In addition, the efficiency of the four models for prediction of risk of healthcare-seeking delay among imported malaria patients was evaluated using the area under curve (AUC) of receiver operating characteristic curve (ROC). The importance of each characteristic was quantified and attributed by using SHAP to examine the positive and negative effects of the value of each characteristic on the predictive efficiency.

RESULTS

A total of 244 imported malaria patients were enrolled, including 100 cases (40.98%) with the duration from onset of first symptoms to time of initial diagnosis that exceeded 24 hours. Logistic regression analysis identified a history of malaria parasite infection [odds ratio (OR) = 3.075, 95% confidential interval (CI): (1.597, 5.923)], long incubation period [OR = 1.010, 95% CI: (1.001, 1.018)] and seeking healthcare in provincial or municipal medical facilities [OR = 12.550, 95% CI: (1.158, 135.963)] as risk factors for delay in seeking healthcare among imported malaria cases. BP neural network modeling showed that duration of residing abroad, incubation period and age posed great impacts on delay in healthcare-seek among imported malaria patients. Random forest modeling showed that the top five factors with the greatest impact on healthcare-seeking delay included main clinical manifestations, the way to go abroad, incubation period, duration of residing abroad and age among imported malaria patients, and Bayesian modeling revealed that the top five factors affecting healthcare-seeking delay among imported malaria patients included level of institutions at initial diagnosis, age, country of origin, history of malaria parasite infection and individuals travelling with imported malaria patients. ROC curve analysis showed higher overall performance of the BP neural network model and the logistic regression model for prediction of the risk of healthcare-seeking delay among imported malaria patients (Z = 2.700 to 4.641, all P values < 0.01), with no statistically significant difference in the AUC among four models (Z = 1.209, P > 0.05). The sensitivity (71.00%) and Youden index (43.92%) of the logistic regression model was higher than those of the BP neural network (63.00% and 36.61%, respectively), and the specificity of the BP neural network model (73.61%) was higher than that of the logistic regression model (72.92%).

CONCLUSIONS

Imported malaria cases with long duration of residing abroad, a history of malaria parasite infection, long incubation period, advanced age and seeking healthcare in provincial or municipal medical institutions have a high likelihood of delay in healthcare-seeking in Jiangsu Province. The models created based on the logistic regression and BP neural network show a high efficiency for prediction of the risk of healthcare-seeking among imported malaria patients in Jiangsu Province, which may provide insights into health management of imported malaria patients.

Exposure to multiple metals in adults and diabetes mellitus: a cross-sectional analysis

Diabetes mellitus (DM) is the most widely recognized metabolic illness with expanding morbidity among ongoing years. Its high incapacity rate and death rate badly affect individuals' quality of life. Increasing proofs backed the relationship between metal exposures with the risk of DM, but the methodological boundedness cannot clarify the complexity of the internal relationship of metal mixtures. We fitted the logistic regression model, weighted quantile sum regression model, and Bayesian kernel machine regression model to assess the relationship between the metal exposures with DM in adults who participated in the National Health and Nutrition Examination Survey 2013-2016. The metals (lead, cadmium, and copper) levels were significantly higher among diabetic compared to the healthy controls. In the logistic regression model established for each single metal, lead and manganese were associated with DM in both unadjusted and mutually adjusted models (highest vs. lowest concentration quartile). When considering all metal as a mixed exposure, we found a generally positive correlation between metal mixtures with DM (binary outcome) and glycohemoglobin (HbA1c) levels (continuous outcome). Exposure to metal mixtures was associated with an increased risk of DM and elevated levels of HbA1c.

The design of early warning software systems for financial crises in high-tech businesses using fusion models in the context of sustainable economic growth

Enterprises are urged to continue implementing the sustainable development strategy in their business operations as "carbon neutrality" and "carbon peak" gradually become the current stage's worldwide targets. High-tech businesses (HTE) need to be better equipped to manage financial risks and avoid financial crises in the face of severe market competition. The most popular machine learning models-logistic regression, XGBoost, and BP neural networks-are chosen as the base models in this study. The three models are combined using the stacking method to train and forecast the fusion models while offering other researchers some basic model research ideas. The financial crisis early warning (FCEW) of HTE is built concurrently by contrasting the fusion of various quantitative basis models and the fusion procedures of voting and averaging. The outcomes demonstrate that the fusion model outperforms the single model in terms of performance, and the stacked fusion model has the best early warning impact. By comparing and comparing the effect of three fusion models on financial crisis warnings of high-tech enterprises, it makes up for the defect of low accuracy of traditional forecasting methods. It improves the sustainable development path of enterprises.

Diagnostic signature composed of seven genes in HIF-1 signaling pathway for preeclampsia

PURPOSE

In this study, we explored the relationship of genes in HIF-1 signaling pathway with preeclampsia and establish a logistic regression model for diagnose preeclampsia using bioinformatics analysis.

METHOD

Two microarray datasets GSE75010 and GSE35574 were downloaded from the Gene Expression Omnibus database, which was using for differential expression analysis. DEGs were performed the Gene Ontology (GO) analysis, Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis and Gene set enrichment analysis (GSEA). Then we performed unsupervised consensus clustering analysis using genes in HIF-1 signaling pathway, and clinical features and immune cell infiltration were compared between these clusters, as well as the least absolute shrinkage and selection operator (LASSO) method to screened out key genes to constructed logistic regression model, and receiver operating characteristic (ROC) curve was plotted to evaluate the accuracy of the model.

RESULTS

57 DEGs were identified, of which GO, KEGG and analysis GSEA showed DEGs were mostly involved in HIF-1 signaling pathway. Two subtypes were identified of preeclampsia and 7 genes in HIF1-signaling pathway were screened out to establish the logistic regression model for discrimination preeclampsia from controls, of which the AUC are 0.923 and 0.845 in training and validation datasets respectively.

CONCLUSION

Seven genes (including MKNK1, ARNT, FLT1, SERPINE1, ENO3, LDHA, BCL2) were screen out to build potential diagnostic model of preeclampsia.

Research on regional water environmental carrying capacity based on GIS and TOPSIS comprehensive evaluation model

Water environmental carrying capacity (WECC) is an important indicator for assessing the coordination between the water environment and the social-economic-resources and environment subsystems. In this study, to determine the WECC of Changsha-Zhuzhou-Xiangtan urban agglomeration in Xiang River Basin, a three-level index system was established using an analytic hierarchy process. Because the previous evaluation system lacked continuous indicators, the results could not reflect the differences of WECC within the administrative units, thus, this study selected 4 continuous indicators, and finally an evaluation index system including 15 indicators was established. Based on the TOPSIS model and logistic regression model, the current situation and change trend of WECC in the study area were obtained in ArcGIS. The results showed that the comprehensive WECC in this region was inferior in 2020, particularly in urban concentrated areas, and it was extremely uneven in spatial distribution. The WECC decreased significantly from 2011 to 2014 and gradually improved from 2014 to 2020. According to the prediction results, the WECC will increase in the future, with an average value of 0.54 in 2025 and 0.60 in 2035. This study will have important guiding implications for the protection and improvement of the water environment in the study area and related areas.

The association of trace elements with arthritis in US adults: NHANES 2013-2016

BACKGROUND

Arthritis is a common chronic disease, and is a major cause of disability and chronic pain in adults. Considering inflammatory responses is closely related with trace elements (TEs), the role of TEs in arthritis has attracted much attention. This study aimed to assess the association between TEs and arthritis.

METHODS

Concentrations of TEs in whole blood [cadmium (Cd), lead (Pb), mercury (Hg), selenium (Se), and manganese (Mn)] and serum [copper (Cu) and zinc (Zn)] were measured in adults who participated in the US National Health and Nutrition Examination Survey. Logistic regression model and Bayesian kernel machine regression model were used to explore the association between TEs and arthritis.

RESULTS

The levels of five TEs (Pb, Hg, Cd, Se, and Cu) in the arthritis group changed significantly. Three TEs were found to be associated with an increased risk of arthritis: Pb [OR (95% CI): 2.96 (2.18, 4.03), p-value for trend (P-t) < 0.001], Cd [OR (95% CI): 2.28 (1.68, 3.11), P-t < 0.001], Cu [OR (95% CI): 2.05 (1.53, 2.76), P-t < 0.001]. The Relative Excess Risk of Interaction was 0.35 (95% CI: 0.06-0.65) and 0.38 (95% CI: 0.11-0.64), respectively, suggesting that Hg ions and Se ions have positive additional interactions with alcohol consumption, which reduced the risk of arthritis. Subgroup analysis showed that Pb ions and Cd ions were significantly correlated with osteoarthritis and rheumatoid arthritis.

CONCLUSION

Elevated concentrations of Pb, Cd, and Cu were associated with increased risk of arthritis. Drinking with high levels of Hg or Se may be a protective factor for arthritis. Future studies are warranted to validate these findings in prospective studies.

Expression of EMT-related genes in lymph node metastasis in endometrial cancer: a TCGA-based study

BACKGROUND

Endometrial cancer (EC) with metastasis in pelvic/para-aortic lymph nodes suggests an unsatisfactory prognosis. Nevertheless, there is still rare literature focusing on the role of epithelial-mesenchymal transition (EMT) in lymph node metastasis (LNM) in EC.

METHODS

Transcriptional data were derived from the TCGA database. Patients with stage IA-IIIC2 EC were included, constituting the LN-positive and LN-negative groups. To evaluate the extent of EMT, an EMT signature composed of 315 genes was adopted. The EMT-related genes (ERGs) were obtained from the dbEMT2 database, and the differentially expressed ERGs (DEERGs) between these two groups were screened. On the basis of DEERGs, pathway analysis was carried out. We eventually adopted the logistic regression model to build an ERG-based gene signature with predictive value for LNM in EC.

RESULTS

A total of 498 patients were included, with 75 in the LN-positive group. Median EMT score of tumor tissues from LN-negative group was - 0.369, while that from the LN-positive group was - 0.296 (P < 0.001), which clearly exhibited a more mesenchymal phenotype for LNM cases on the EMT continuum. By comparing expression profiles, 266 genes were identified as DEERGs, in which 184 were upregulated and 82 were downregulated. In pathway analysis, various EMT-related pathways were enriched. DEERGs shared between molecular subtypes were comparatively few. The ROC curve and logistic regression analysis screened 7 genes with the best performance to distinguish between the LN-positive and LN-negative group, i.e., CIRBP, DDR1, F2RL2, HOXA10, PPARGC1A, SEMA3E, and TGFB1. A logistic regression model including the 7-gene-based risk score, age, grade, myometrial invasion, and histological subtype was built, with an AUC of 0.850 and a favorite calibration (P = 0.074). In the validation dataset composed of 83 EC patients, the model exhibited a satisfactory predictive value and was well-calibrated (P = 0.42).

CONCLUSION

The EMT status and expression of ERGs varied in LNM and non-LNM EC tissues, involving multiple EMT-related signaling pathways. Aside from that, the distribution of DEERGs differed among molecular subtypes. An ERG-based gene signature including 7 DEERGs exhibited a desirable predictive value for LNM in EC, which required further validation based upon clinical specimens in the future.

A novel machine learning model and a public online prediction platform for prediction of post-ERCP-cholecystitis (PEC)

BACKGROUND

Endoscopic retrograde cholangiopancreatography (ERCP) is an established treatment for common bile duct (CBD) stones. Post- ERCP cholecystitis (PEC) is a known complication of such procedure and there are no effective models and clinical applicable tools for PEC prediction.

METHODS

A random forest (RF) machine learning model was developed to predict PEC. Eligible patients at The First Hospital of Lanzhou University in China with common bile duct (CBD) stones and gallbladders in-situ were enrolled from 2010 to 2019. Logistic regression analysis was used to compare the predictive discrimination and accuracy values based on receiver operation characteristics (ROC) curve and decision and clinical impact curve. The RF model was further validated by another 117 patients. This study was registered with ClinicalTrials.gov, NCT04234126.

FINDINGS

A total of 1117 patients were enrolled (90 PEC, 8.06%) to build the predictive model for PEC. The RF method identified white blood cell (WBC) count, endoscopic papillary balloon dilatation (EPBD), increase in WBC, residual CBD stones after ERCP, serum amylase levels, and mechanical lithotripsy as the top six predictive factors and has a sensitivity of 0.822, specificity of 0.853 and accuracy of 0.855, with the area under curve (AUC) value of 0.890. A separate logistic regression prediction model was built with sensitivity, specificity, and AUC of 0.811, 0.791, and 0.864, respectively. An additional 117 patients (11 PEC, 9.40%) were used to validate the RF model, with an AUC of 0.889 compared to an AUC of 0.884 with the logistic regression model.

INTERPRETATION

The results suggest that the proposed RF model based on the top six PEC risk factors could be a promising tool to predict the occurrence of PEC.

Patient-reported adherence to physical exercises of patients with ankylosing spondylitis

Introduction

Studies on adherence to exercise therapy of patients with ankylosing spondylitis (AS) are rare, and the criteria for adherence to exercise are inconsistent. This study aimed to quantify patient-reported adherence to exercise therapy of Chinese outpatients with AS and investigate the factors related to poor adherence.

Methods

The subjects’ sociodemographic, disease-related, radiographic, and laboratory parameters were collected. Patients’ adherence to exercise therapy was assessed using the Exercise Attitude Questionnaire (EAQ) with a 4-point Likert scale. All cases were grouped as good adherence and poor adherence using a cutoff score of 60, according to a previous study. Univariate analysis was conducted to assess the intergroup differences. Then, we built a multivariate logistic regression model to identify possible significant factors related to poor adherence to exercise therapy.

Results

A total of 185 outpatients completed the questionnaire. The mean EAQ score was 49.4 (IQR, 40.7–59.3) and 146 patients (78.9%) were considered to have poor adherence, and 39 patients (21.1%) were considered to have good adherence. The rates of current nonsteroidal anti-inflammatory drugs (NSAIDs), conventional synthetic disease-modifying antirheumatic drugs (csDMARDs), and tumor necrosis factor-α inhibitor (TNF-i) use were significantly higher in the poor adherence group (p=0.001, p=0.027, p=0.018, respectively). Our multivariate logistic regression model revealed that the only significant associated factor was current use of NSAIDs (OR=3.517; p=0.016; 95% CI, 1.259–9.827).

Conclusions

Outpatients with AS had an unacceptable level of adherence to exercise therapy, and current use of NSAIDs was a significantly associated factor.

Key Points • Outpatients with AS had an unacceptable level of adherence to exercise therapy. • Current use of NSAIDs exerted a negative impact on patients’ adherence to exercise therapy.

CD10 and Das1: a biomarker study using immunohistochemistry to subtype gastric intestinal metaplasia

Background

Intestinal metaplasia (IM) is considered a key pivot point in the Correa model of gastric cancer (GC). It is histologically subtyped into the complete and incomplete subtypes, the latter being associated with a greater risk of progression. However, the clinical utility of IM subtyping remains unclear, partially due to the absence of reliable defining biomarkers.

Methods

Based on gene expression data and existing literature, we selected CD10 and Das1 as candidate biomarkers to distinguish complete and incomplete IM glands in tissues from patients without GC (IM-GC) and patients with GC (IM + GC). Immunohistochemical staining of individually subtyped IM glands was scored after blinding by two researchers using tissue belonging to both IM-GC and IM + GC patients. Whole tissue Das1 staining was further assessed using digital image quantification (cellSens Dimension, Olympus).

Results

Across both cohorts CD10 stained the IM brush border and was shown to have a high sensitivity (87.5% and 94.9% in IM-GC and IM + GC patients respectively) and specificity (100.0% and 96.7% respectively) with an overall AUROC of 0.944 for complete IM glands. By contrast Das1 stained mainly goblet cells and the apical membrane of epithelial cells, mostly of incomplete IM glands with a low sensitivity (28.6% and 29.3% in IM-GC and IM + GC patients respectively) but high specificity (98.3% and 85.1% respectively) and an overall AUROC of 0.603 for incomplete IM glands. A combined logistic regression model showed a significant increase in AUROC for detecting complete IM glands (0.955 vs 0.970). Whole tissue digital quantification of Das1 staining showed a significant association with incomplete IM compared to complete IM, both in IM-GC and in IM + GC patients (p = 0.016 and p = 0.009 respectively, Mann–Whitney test and unpaired t test used). Additionally, complete IM in IM + GC patients exhibited significantly more Das1 staining than in IM-GC patients (p = 0.019, Mann–Whitney test).

Conclusions

These findings suggest that CD10 is an outstanding biomarker for complete IM and Das1 may be useful as a secondary biomarker for IM glands at greater risk of progression irrespective of IM subtype. Overall, the clinical use of these biomarkers could lead to improved patient stratification and targeted surveillance.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12876-022-02268-z.

Multiparametric transrectal ultrasound for the diagnosis of peripheral zone prostate cancer and clinically significant prostate cancer: novel scoring systems

Background

To evaluate the diagnostic performance of multiparametric transrectal ultrasound (TRUS) and to design diagnostic scoring systems based on four modes of TRUS to predict peripheral zone prostate cancer (PCa) and clinically significant prostate cancer (csPCa).

Methods

A development cohort involved 124 nodules from 116 patients, and a validation cohort involved 72 nodules from 67 patients. Predictors for PCa and csPCa were extracted to construct PCa and csPCa models based on regression analysis of the development cohort. An external validation was performed to assess the performance of models using area under the curve (AUC). Then, PCa and csPCa diagnostic scoring systems were established to predict PCa and csPCa. The diagnostic accuracy was compared between PCa and csPCa scores and PI-RADS V2, using receiver operating characteristics (ROC) and decision curve analysis (DCA).

Results

Regression models were established as follows: PCa = − 8.284 + 4.674 × Margin + 1.707 × Adler grade + 3.072 × Enhancement patterns + 2.544 × SR; csPCa = − 7.201 + 2.680 × Margin + 2.583 × Enhancement patterns + 2.194 × SR. The PCa score ranged from 0 to 6 points, and the csPCa score ranged from 0 to 3 points. A PCa score of 5 or higher and a csPCa score of 3 had the greatest diagnostic performance. In the validation cohort, the AUC for the PCa score and PI-RADS V2 in diagnosing PCa were 0.879 (95% confidence interval [CI] 0.790–0.967) and 0.873 (95%CI 0.778–0.969). For the diagnosis of csPCa, the AUC for the csPCa score and PI-RADS V2 were 0.806 (95%CI 0.700–0.912) and 0.829 (95%CI 0.727–0.931).

Conclusions

The multiparametric TRUS diagnostic scoring systems permitted better identifications of peripheral zone PCa and csPCa, and their performances were comparable to that of PI-RADS V2.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12894-022-01013-8.

Effect of nursing model based on risk prediction with Logistic regression model on recovery of gastrointestinal motility function and quality of life in patients after gynecological laparoscopy

BACKGROUND

Laparoscopic surgery is a common treatment in gynecology. Although it is a typical minimally invasive procedure, postoperative complications still exist and affect early postoperative recovery. Logistic regression models can be developed to obtain the weights of independent variables and to understand the risk factors for postoperative complications after laparoscopy, which can help to develop intervention strategies.

AIM

To evaluate the effect of a nursing model based on the risk prediction with a Logistic regression model on the early postoperative recovery, gastrointestinal motility, and quality of life in patients after gynecological laparoscopy.

METHODS

The case data of 232 patients undergoing gynecological laparoscopy at our hospital from January 2019 to January 2021 were selected to construct a Logistic regression model to predict the independent risk factors and incidence of gastrointestinal dysfunction after gynecological laparoscopy. Ninety-eight patients who would undergo gynecological laparoscopic surgery were prospectively selected and divided into either a control group or an observation group according to the order in which they were filed, with 49 cases in each group. The control group was given routine care, and the observation group adopted a care model based on the risk prediction using the Logistic regression model. The postoperative recovery status (time to first exhaust, time to first defecation, time to recovery of bowel sounds, and time to gastrointestinal peristalsis) and quality of life were compared between the two groups.

RESULTS

Among 232 patients undergoing gynecological laparoscopy, the incidence of postoperative gastrointestinal dysfunction was 38.36%. Logistic regression analysis showed that age ≥ 60 years old, time to postoperative start of activity ≥ 3 d, drainage tube indwelling time ≥ 7 d, abnormal postoperative potassium, no use of postoperative analgesia, and no use of postoperative gastrointestinal motility drugs were independent risk factors for gastrointestinal dysfunction after gynecological laparoscopic surgery (P < 0.05). Based on these independent risk factors, a Logistic regression model was constructed, and the receiver operating characteristic curve (ROC) was drawn based on the predicted value and the true value. When Logistic (P) was > 0.209, the area under the curve was 0.859, the predictive sensitivity was 95.92%, and the specificity was 93.27%. The time to first exhaustion, time to first defecation, time to bowel sound recovery, and time to gastrointestinal peristalsis were shorter in the observation group than in the control group (P < 0.05). After intervention, the quality of life of patients in the observation group was significantly better than that of the control group (P < 0.05).

CONCLUSION

The nursing model based on risk prediction using a Logistic regression model can promote the early recovery of patients undergoing gynecological laparoscopy, accelerate the recovery of gastrointestinal function, and improve their postoperative quality of life.

Assessing poverty and livelihood vulnerability of the fishing communities in the context of pollution of the Churni River, India

The present study exhibits a critical outlook on the poverty and livelihood vulnerability of the fisherman community in the context of persistent water pollution of the Churni River. The logistic regression model has identified eight factors influencing the poverty of the study area while the entropy weight method identifies the livelihood vulnerability of the fishermen. The livelihood vulnerability index of the upper stretch of the river is higher (0.65-0.67) compared to that of the lower stretch (0.46-0.57). The typical spatiality in poverty and livelihood vulnerability is triggered by the fragility of fishing livelihoods in the wake of lower concentrations of dissolved oxygen (DO), and higher BOD, COD, ammonia, nitrate and phosphate mainly due to industrial water pollution. For example, average DO ranges from 1.65 mg/l (upper stretch) to 2.50 mg/l (lower stretch) while the average BOD ranges from 5.44 mg/l (lower stretch) to 9.42 mg/l (upper stretch). This pollution induces acute ecological stress concerning declining fish diversity (from 41 to 16 fish species at the upper stretch and 41 to 23 fish species at the lower stretch during 1980-2018) as well as productivity of the existing fish species. Therefore, paralysed fishing economy and high dependency of the fishermen on the Churni River have forced them to revolve into the vicious cycle of poverty and enduring fragile livelihoods. Thus, the fishermen adopt few coping strategies like access to the nearby wetland for fishing, diversity in earning strategy and environmental movements against pollution to reduce the intensity of vulnerability. The present study would help the regional planners to frame the participatory plans for the sustainability of the riverine ecology and economy.

Efficacy of logistic regression model based on multiparametric ultrasound in assessment of cervical lymphadenopathy - a retrospective study

OBJECTIVES

To investigate whether a multiparametric ultrasound (MPUS) diagnostic model improves differential diagnosis of benign and malignant cervical lymph nodes.

METHODS

MPUS evaluation was performed on 87 lesions in 86 patients, and related characteristics and parameters of the patients and lesions were studied and logistic regression models based on the MPUS characteristics of cervical lymph nodes were built. A receiver operating characteristic curve and area under the curve (AUC) were built for the evaluation of diagnostic performances.

RESULTS

Of the 87 lesions in 86 patients, there were 31 benign and 56 malignant lesions. Regression models for Duplex ultrasound and MPUS were established. The Duplex ultrasound regression model showed a sensitivity, specificity, positive predictive value and negative predictive value of 94.4, 61.3, 86.3 and 80.9%, respectively. The predictive accuracy was 82.4%, and the AUC was 0.861. The MPUS regression model showed a sensitivity, specificity, positive predictive value and negative predictive value of 98.1, 61.3, 81.5 and 95.0%, respectively. The predictive accuracy was 84.7%, and the AUC was 0.894. The differences in AUCs between the Duplex ultrasound model and MPUS model, ultrasound model and ultrasonic elastography (UE), and Duplex ultrasound and UE were not significant (all p > 0.05); the differences in AUCs between the MPUS model and Duplex ultrasound, Duplex ultrasound model and Duplex ultrasound, and MPUS model and UE were significant (all p < 0.05).

CONCLUSIONS

The Duplex ultrasound and MPUS models achieve significantly higher diagnostic performance for differentiating between benign and malignant cervical lymph nodes.

Are there differences in the forces driving the conversion of different non-urban lands into urban use? A case study of Beijing

Examining the heterogeneous factors behind the conversion of various types of non-urban land into urban use is of great significance for controlling urban land expansion and formulating reasonable land use policies. Taking Beijing as an example, this study identified the spatial patterns of urban expansion in China's large cities and then explored the different driving factors behind its various sources. The results showed that, from 2001 to 2010, Beijing's urban land presented a compound expansion mode in which multiple spatial modes coexisted. Urban encroachment contributed differently to the loss of different non-urban lands. Cultivated land and ecological land were the main sources of newly developed urban land, of which the conversion was driven jointly by topography, location, transportation, socioeconomic development, and spatial planning. Moreover, the main factors behind the conversion of various land types varied: closing to existing built-up area and infrastructures increases the conversion probability of most land types; socioeconomic development has common but differentiated effects; governments at different levels have their influences on the conversion of different types of non-urban land. Based on the results, this study suggested the importance of considering varied approaches in managing non-urban lands to better controlling their conversion into urban use and the different roles that could be played by governments at various levels.

Acute malnutrition and its determinants of preschool children in Bangladesh: gender differentiation

Background

Children acute malnutrition (AM) is a global public health concern, especially in low and middle income countries. AM is associated with multiple physiological vulnerabilities, including immune dysfunction, enteric barrier disruption, gut microbiome dysbiosis, and essential nutrient deficits. This study aimed to determine the prevalence of AM and its associated factors among preschool children in Rajshahi district, Bangladesh.

Methods

This cross-sectional study was conducted from October to December, 2016. Children acute malnutrition was assessed using mid-upper arm circumference. Multiple binary logistic regression analyses were employed to determine the associated factors after adjusting the effect of independent factors of children AM.

Result

The prevalence of AM amongst preschool children was 8.7%, among them 2.2 and 6.5% were severe acute malnutrition and moderate acute malnutrition, respectively. Z-proportional test demonstrated that the difference in AM between girls (11.6) and boys (5.9%) was significant (p < 0.05). Children AM was associated with being: (i) children aged 6–23 months (aOR = 2.29, 95% CI: 1.20–4.37; p < 0.05), (ii) early childbearing mothers’ (age < 20 years) children (aOR = 3.06, 95% CI: 1.08–8.66; p < 0.05), (iii) children living in poor family (aOR = 3.08, 95% CI: 1.11–8.12; p < 0.05), (iv) children living in unhygienic latrine households (aOR = 2.81, 95% CI: 1.52–5.09; p < 0.01), (v) Hindu or other religion children (aOR = 0.42, 95% CI: 0.19–0.92; p < 0.05).

Conclusion

The prevalence of AM was high among these preschool children. Some modifiable factors were associated with AM of preschool children. Interventions addressing social mobilization and food security could be an effective way to prevent acute malnutrition among children in Bangladesh.

A nomogram for bladder pain syndrome/interstitial cystitis based on netrin-1

Purpose

This study aimed to combine plasma netrin-1 and clinical parameters to construct a diagnostic model for bladder pain syndrome/interstitial cystitis (BPS/IC).

Methods

We analyzed the independent diagnostic value of netrin-1 and the correlation with clinical symptom scores of BPS/IC. Clinical parameters were selected using LASSO regression, and a multivariate logistic regression model based on netrin-1 was established, and then a nomogram of BPS/IC prevalence was constructed. The nomogram was evaluated using calibration curves, the C-index, and decision curve analysis (DCA). Finally, the model was validated using an internal validation method.

Results

The area under the curve for the ability of netrin-1 to independently predict BPS/IC diagnosis was 0.858 (p < 0.001), with a sensitivity of 85% and specificity of 82%. The predicted nomogram included three variables: age, CD3 + /CD4 + T lymphocyte ratio, and netrin-1. The C-index of this nomogram was 0.882, and the predicted values were highly consistent with the actual results in the calibration curve. In addition, the internally validated C-index of 0.870 confirms the high reliability of the model. DCA results show that the net patient benefit of the netrin-1 combined with other clinical parameters was higher than that of the single netrin-1 model.

Conclusion

Netrin-1 can be used as a diagnostic marker for BPS/IC and is associated with pain. The nomogram constructed by combining netrin-1 and clinical parameters was able to predict BPS/IC with great accuracy. In addition, Netrin-1 may also serve as a novel therapeutic target for BPS/IC.

Logit model in prospective coronary heart disease (CHD) risk factors prediction in Saudi population

Analysis through logistic regression explored to investigate the relationship between binary or multivariable ordinal response probability and in one or more explanatory variables. The main objectives of this study to investigate advanced prediction risk factor of Coronary Heart Disease (CHD) using a logit model. Attempts made to reduce risk factors, increase public or professional awareness. Logit model used to evaluate the probability of a person develop CHD, considering any factors such as age, gender, high low-density lipoprotein (LDL) cholesterol, low high-density lipoprotein (HDL) cholesterol, high blood pressure, family history of CHD younger than 45, diabetes, smoking, being post-menopausal for women and being older than 45 for men. Logit concept of brief statistics described with slight modification to estimate the parameters testing for the significance of the coefficients, confidence interval fits the simple, multiple logit models. Besides, interpretation of the fitted logit regression model introduced. Variables showing best results within the scientific context, good explanation data assessed to fit an estimated logit model containing chosen variables, this present experiment used the statistical inference procedure; chi-square distribution, likelihood ratio, Score, or Wald test and goodness-of-fit. Health promotion started with increased public or professional awareness improved for early detection of CHD, to reduce the risk of mortality, aimed to be Saudi vision by 2030.

Predicting asymptomatic neurosyphilis using peripheral blood indicators

Background

The high misdiagnosis rate of asymptomatic neurosyphilis (ANS) has long challenged infectious disease clinicians. We aim to develop a model for diagnosing ANS in asymptomatic syphilis (AS) patients without CSF indicators.

Results

277 AS patients with HIV-negative and underwent lumbar puncture were enrolled in this horizontal study.The area under the curve for predicting ANS by CSF leukocytes and protein was 0.643 and 0.675 [95% CI, 0.583–0.699VS.0.616–0.729]. Through LRM, the AUC increased to 0.806 [95% CI, 0.732–0.832], and the Youden's index was 0.430. If the score is ≤ 0.159, ANS can be excluded with a predictive value of 92.9%; we can identify ANS while the score is over 0.819, with a predictive value of 91.7% and a specificity of 99.25%. This study showed that the LRM can diagnose ANS in AS patients effectively.

Conclusion

Given a large number of misdiagnosis ANS patients and CSF results' insufficiency, the model is more practical. Our research will help clinicians track suspected syphilis, especially those who cannot accept the CSF test.

Establishment and validation of a logistic regression model for prediction of septic shock severity in children

Background

Septic shock is the most severe complication of sepsis, and is a major cause of childhood mortality, constituting a heavy public health burden.

Methods

We analyzed the gene expression profiles of septic shock and control samples from the Gene Expression Omnibus (GEO). Four differentially expressed genes (DEGs) from survivor and control groups, non-survivor and control groups, and survivor and non-survivor groups were selected. We used data about these genes to establish a logistic regression model for predicting the survival of septic shock patients.

Results

Leave-one-out cross validation and receiver operating characteristic (ROC) analysis indicated that this model had good accuracy. Differential expression and Gene Set Enrichment Analysis (GSEA) between septic shock patients stratified by prediction score indicated that the systemic lupus erythematosus pathway was activated, while the limonene and pinene degradation pathways were inactivated in the high score group.

Conclusions

Our study provides a novel approach for the prediction of the severity of pathology in septic shock patients, which are significant for personalized treatment as well as prognostic assessment.

Supplementary Information

The online version contains supplementary material available at 10.1186/s41065-021-00206-9.

The diagnostic value of the combination of carcinoembryonic antigen, squamous cell carcinoma-related antigen, CYFRA 21-1, neuron-specific enolase, tissue polypeptide antigen, and progastrin-releasing peptide in small cell lung cancer discrimination

BACKGROUND

The diagnostic value of six tumor markers was investigated and the appropriate combinations of those tumor markers to discriminate small cell lung cancer was explored.

METHODS

Patients suspected with lung cancer (1938) were retrospectively analyzed. Candidate tumor markers from carcinoembryonic antigen (CEA), squamous cell carcinoma-related antigen (SCC), cytokeratin 19 fragment 21-1 (CYFRA 21-1), neuron-specific enolase (NSE), tissue polypeptide antigen (TPA), and progastrin releasing peptide (ProGRP) were selected to construct a logistic regression model. The receiver operating characteristic curve was used for evaluating the diagnostic value of the tumor markers and the predictive model.

RESULTS

ProGRP had the highest positive rate (72.3%) in diagnosed small cell lung cancer, followed by neuron-specific enolase (68.3%), CYFRA21-1 (50.5%), carcinoembryonic antigen (45.5%), tissue polypeptide antigen (30.7%), and squamous cell carcinoma-related antigen (5.9%). The predictive model for small cell lung cancer discrimination was established, which yielded the highest area under the curve (0.888; 95% confidence interval: 0.846-0.929), with a sensitivity of 71.3%, a specificity of 95.0%, a positive predictive value of 49.0%, and a negative predictive value of 98.0%.

CONCLUSIONS

Combining tumor markers can improve the efficacy for small cell lung cancer discrimination. A predictive model has been established in small cell lung cancer differential diagnosis with preferable efficacy.

A 3-Gene-Based Diagnostic Signature in Alzheimer's Disease

BACKGROUND

Alzheimer's disease (AD) is a chronic neurodegenerative disease. In this study, potential diagnostic biomarkers were identified for AD.

METHODS

All AD samples and healthy samples were collected from 2 datasets in the GEO database, in which differentially expressed genes (DEGs) were analyzed by using the limma package of R language. GO and KEGG pathway enrichment was conducted basing on the DEGs via the clusterProfiler package of R. And, the PPI network construction and gene prediction were performed using the STRING database and Cytoscape. Then, a logistic regression model was constructed to predict the sample type.

RESULTS

Bioinformatic analysis of GEO datasets revealed 2,063 and 108 DEGs in GSE5281 and GSE4226 datasets, separately, and 15 overlapping DEGs were found. GO and KEGG enrichment analysis revealed terms associated with neurodevelopment. Then, we built a logistic regression model based on the hub genes from the PPI network and optimized the model to 3 genes (ALDOA, ENC1, and NFKBIA). The values of area under the curve of the training set GSE5281 and testing set GSE4226 were 0.9647 and 0.7857, respectively, which implied the efficacy of this model.

CONCLUSION

The comprehensive bioinformatic analysis of gene expression in AD patients and the effective logistic regression model built in our study may provide promising research value for diagnostic methods of AD.

A study of freeway crash risk prediction and interpretation based on risky driving behavior and traffic flow data

The prediction of traffic crashes is an essential topic in traffic safety research. Most of the previous studies conducted experiments on real-time crash prediction of expressways or freeways, based on traffic flow data. However, the influence of risky driving behavior on traffic crash risk prediction has rarely been considered. Thus, a traffic crash risk prediction model based on risky driving behavior and traffic flow has been developed. The data employed in this research were captured using the in-vehicle AutoNavigator software. A random forest to select variables with strong impacts on crashes and the synthetic minority oversampling technique (SMOTE) to adjust the imbalanced dataset were included in the research. A logistic regression model was developed to predict the risk of traffic crash and to interpret its relationship with traffic flow and risky driving behavior characteristics. This model accurately predicted 84.48% of the crashes, while its false alarm rate remained as low as 9.75%, which indicated that this traffic crash risk prediction model had high accuracy. By analyzing the relationship between traffic flow, risky driving behavior, and crashes through partial dependency plots (PDPs), the impact of traffic flow and risky driving behavior variables on certain traffic crashes in the prediction model were determined. Through this study, the data of traffic flow and risky driving behavior could be used to assess the traffic crash risk on freeways and lay a foundation for traffic safety management.

Coronavirus lockdown and virus suppression: An international analysis

This paper analyses the effect of lockdown against the coronavirus which is one of the fastest growing threats in the world. We focus on three categories of lockdown and group four continents, Asia, America, Europe, and Africa together to assess the effectiveness of such a measure to contain the virus. We also look at a number of variables linked to the spread of the virus to determine the factors affecting the growth of new confirmed cases. We show evidence that countries in Europe are more likely to impose a national lockdown than any other continent. For the empirical analysis, we undertake the cross-sectional regression model, logistic regression model and logistic growth curve as a method to apply the data collected over the period March to June 2020 as this is the data available at the time this paper is composed. The empirical results of this paper indicate that countries which impose the strictest form of lockdown will result in a reduction in growth of new confirmed cases.

Improved window adaptive gray level co-occurrence matrix for extraction and analysis of texture characteristics of pulmonary nodules

BACKGROUND AND OBJECTIVE

Identifying benign and malignant pulmonary nodules is essential for the early diagnosis of lung cancer and targeted surgical resection. This study aimed to differentiate benign from malignant pulmonary nodules based on computed tomography (CT) plain scan texture analysis technique.

METHODS

A total of 47 pulmonary nodules use the improved window adaptive gray level co-occurrence matrix (GLCM) algorithm to extract the texture characteristics of the area of interest. The Fisher coefficient (Fisher), classification error probability joint average correlation coefficient (POE+ACC), mutual information (MI), and the combination of above three methods joint (FPM) were used to select the best texture parameters set. After that, the analysis of the screened texture parameters was adopted. The B11 module provides four analytical methods, including raw data analysis (RDA), principal component analysis (PCA), linear discriminant analysis (LDA), and nonlinear discriminant analysis (NDA). The results were expressed in the form of misclassification rate (MCR). Region of curve (ROC) analysis was also performed on the selected optimal texture parameters.

RESULTS

The MCR of all the three texture feature extraction methods, Fisher, POE+ACC, and MI, were lower in differentiating benign from malignant pulmonary nodules. FPM method could further reduce the MCR. The NDA analysis had the lowest MCR for both of these three feature extraction methods. The MCR can be further reduced to 2.13% by the combination of NDA and FPM. The ROC curve showed that Perc.01% parameter had the highest AUC value and the most discriminative efficacy.

CONCLUSION

The lowest MCR values were calculated by the FPM dimensionality reduction method and the NDA analysis method. The improved GLCM algorithm has a discriminative role in CT texture analysis of benign and malignant pulmonary nodules.

Coronavirus lockdown and virus suppression: An international analysis

This paper analyses the effect of lockdown against the coronavirus which is one of the fastest growing threats in the world. We focus on three categories of lockdown and group four continents, Asia, America, Europe, and Africa together to assess the effectiveness of such a measure to contain the virus. We also look at a number of variables linked to the spread of the virus to determine the factors affecting the growth of new confirmed cases. We show evidence that countries in Europe are more likely to impose a national lockdown than any other continent. For the empirical analysis, we undertake the cross-sectional regression model, logistic regression model and logistic growth curve as a method to apply the data collected over the period March to June 2020 as this is the data available at the time this paper is composed. The empirical results of this paper indicate that countries which impose the strictest form of lockdown will result in a reduction in growth of new confirmed cases.

Novel Prognostic Models for Predicting the 180-day Outcome for Patients with Hepatitis-B Virus-related Acute-on-chronic Liver Failure

BACKGROUND AND AIMS

It remains difficult to forecast the 180-day prognosis of patients with hepatitis B virus-acute-on-chronic liver failure (HBV-ACLF) using existing prognostic models. The present study aimed to derive novel-innovative models to enhance the predictive effectiveness of the 180-day mortality in HBV-ACLF.

METHODS

The present cohort study examined 171 HBV-ACLF patients (non-survivors, n=62; survivors, n=109). The 27 retrospectively collected parameters included the basic demographic characteristics, clinical comorbidities, and laboratory values. Backward stepwise logistic regression (LR) and the classification and regression tree (CART) analysis were used to derive two predictive models. Meanwhile, a nomogram was created based on the LR analysis. The accuracy of the LR and CART model was detected through the area under the receiver operating characteristic curve (AUROC), compared with model of end-stage liver disease (MELD) scores.

RESULTS

Among 171 HBV-ACLF patients, the mean age was 45.17 years-old, and 11.7% of the patients were female. The LR model was constructed with six independent factors, which included age, total bilirubin, prothrombin activity, lymphocytes, monocytes and hepatic encephalopathy. The following seven variables were the prognostic factors for HBV-ACLF in the CART model: age, total bilirubin, prothrombin time, lymphocytes, neutrophils, monocytes, and blood urea nitrogen. The AUROC for the CART model (0.878) was similar to that for the LR model (0.878, p=0.898), and this exceeded that for the MELD scores (0.728, p<0.0001).

CONCLUSIONS

The LR and CART model are both superior to the MELD scores in predicting the 180-day mortality of patients with HBV-ACLF. Both the LR and CART model can be used as medical decision-making tools by clinicians.

Validation and update of a multivariable prediction model for the identification and management of patients at risk for hepatocellular carcinoma

Background

A hepatocellular carcinoma (HCC) prediction model (ASAP), including age, sex, and the biomarkers alpha-fetoprotein and prothrombin induced by vitamin K absence-II, showed potential clinical value in the early detection of HCC. We validated and updated the model in a real-world cohort and promoted its transferability to daily clinical practice.

Methods

This retrospective cohort analysis included 1012 of the 2479 eligible patients aged 35 years or older undergoing surveillance for HCC. The data were extracted from the electronic medical records. Biomarker values within the test-to-diagnosis interval were used to validate the ASAP model. Due to its unsatisfactory calibration, three logistic regression models were constructed to recalibrate and update the model. Their discrimination, calibration, and clinical utility were compared. The performance statistics of the final updated model at several risk thresholds are presented. The outcomes of 855 non-HCC patients were further assessed during a median of 10.2 months of follow-up. Statistical analyses were performed using packages in R software.

Results

The ASAP model had superior discriminative performance in the validation cohort [C-statistic = 0.982, (95% confidence interval 0.972–0.992)] but significantly overestimated the risk of HCC (intercept − 3.243 and slope 1.192 in the calibration plot), reducing its clinical usefulness. Recalibration-in-the-large, which exhibited performance comparable to that of the refitted model revision, led to the retention of the excellent discrimination and substantial improvements in the calibration and clinical utility, achieving a sensitivity of 100% at the median prediction probability of the absence of HCC (1.3%). The probability threshold of 1.3% and the incidence of HCC in the cohort (15.5%) were used to stratify the patients into low-, medium-, and high-risk groups. The cumulative HCC incidences in the non-HCC patients significantly differed among the risk groups (log-rank test, p-value < 0.001). The 3-month, 6-month and 18-month cumulative incidences in the low-risk group were 0.6%, 0.9% and 0.9%, respectively.

Conclusions

The ASAP model is an accurate tool for HCC risk estimation that requires recalibration before use in a new region because calibration varies with clinical environments. Additionally, rational risk stratification and risk-based management decision-making, e.g., 3-month follow-up recommendations for targeted individuals, helped improve HCC surveillance, which warrants assessment in larger cohorts.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12014-021-09326-w.

Candidate symptomatic markers for predicting violence in schizophrenia: A cross-sectional study of 7711 patients in a Chinese population

OBJECTIVE

Violent behaviour is an alarming problem among schizophrenia patients. The effects of historical, clinical, and pathological risk factors for violence have been investigated by multiple studies, but consensus has not been achieved. As psychotic symptoms are more direct and intuitive indicators for violence, identifying robustly associated symptoms is a crucial part of the future prediction and precise management of violent patients in clinics. This study aims to identify the psychotic symptoms correlated with violence among schizophrenia patients in a Chinese population.

METHODS

In this cross-sectional study, the medical records of 7711 schizophrenia patients (4711 in the discovery set and 3000 in the validation set) were collected from 1998 to 2010. Their psychotic symptoms were extracted, and the patients were divided into violent and non-violent groups. Multivariate logistic analysis was applied to identify symptoms associated with violence in the discovery set.

RESULTS

Eight psychotic symptoms were found to be significantly correlated with violence in schizophrenia. "Destruction of property", "verbal aggression" and "insomnia" increased the risk of violence, while "flat affect", "delusion of persecution", "auditory hallucination", "vagueness of thought" and "poverty of thought" decreased the risk of violence. The regression model was evaluated by receiver operating characteristic (ROC) analysis for its discriminatory performance, achieving area under curve (AUC) values of 0.887 in the discovery sample set and 0.824 in the validation sample set.

CONCLUSIONS

The correlated symptoms identified by this study can serve as future candidate predictors for violence in schizophrenia, paving the way for precise management of schizophrenia patients in clinics.

A 2 miRNAs-based signature for the diagnosis of atherosclerosis

BACKGROUND

Atherosclerosis (AS) is a leading cause of vascular disease worldwide. MicroRNAs (miRNAs) play an essential role in the development of AS. However, the miRNAs-based biomarkers for the diagnosis of AS are still limited. Here, we aimed to identify the miRNAs significantly related to AS and construct the predicting model based on these miRNAs for distinguishing the AS patients from healthy cases.

METHODS

The miRNA and mRNA expression microarray data of blood samples from patients with AS and healthy cases were obtained from the GSE59421 and GSE20129 of Gene Expression Omnibus (GEO) database, respectively. Weighted Gene Co-expression Network Analysis (WGCNA) was performed to evaluate the correlation of the miRNAs and mRNAs with AS and identify the miRNAs and mRNAs significantly associated with AS. The potentially critical miRNAs were further optimized by functional enrichment analysis. The logistic regression models were constructed based on these optimized miRNAs and validated by threefold cross-validation method.

RESULTS

WGCNA revealed 42 miRNAs and 532 genes significantly correlated with AS. Functional enrichment analysis identified 12 crucial miRNAs in patients with AS. Moreover, 6 miRNAs among the identified 12 miRNAs, were selected using a stepwise regression model, in which four miRNAs, including hsa-miR-654-5p, hsa-miR-409-3p, hsa-miR-485-5p and hsa-miR-654-3p, were further identified through multivariate regression analysis. The threefold cross-validation method showed that the AUC of logistic regression model based on the four miRNAs was 0.7308, 0.8258, and 0.7483, respectively, with an average AUC of 0.7683.

CONCLUSION

We identified a total of four miRNAs, including hsa-miR-654-5p and hsa-miR-409-3p, are identified as the potentially critical biomarkers for AS. The logistic regression model based on the identified 2 miRNAs could reliably distinguish the patients with AS from normal cases.

Machine learning analysis of gene expression profile reveals a novel diagnostic signature for osteoporosis

Background

Osteoporosis (OP) is increasingly prevalent with the aging of the world population. It is urgent to identify efficient diagnostic signatures for the clinical application.

Method

We downloaded the mRNA profile of 90 peripheral blood samples with or without OP from GEO database (Number: GSE152073). Weighted gene co-expression network analysis (WGCNA) was used to reveal the correlation among genes in all samples. GO term and KEGG pathway enrichment analysis was performed via the clusterProfiler R package. STRING database was applied to screen the interaction pairs among proteins. Protein–protein interaction (PPI) network was visualized based on Cytoscape, and the key genes were screened using the cytoHubba plug-in. The diagnostic model based on these key genes was constructed, and 5-fold cross validation method was applied to evaluate its reliability.

Results

A gene module consisted of 176 genes predicted to be associated with the occurrence of OP was identified. A total of 16 significantly enriched GO terms and 1 significantly enriched KEGG pathway were obtained based on the 176 genes. The top 50 key genes in the PPI network were identified. Then 22 genes were screened based on stepwise regression analysis from the 50 key genes. Of which, 9 genes were further screened out by multivariate regression analysis with the significant threshold of P value < 0.01. The diagnostic model was established based on the optimal 9 key genes, which efficiently separated the normal samples and OP samples.

Conclusion

A diagnostic model established based on nine key genes could reliably separate OP patients from healthy subjects, which provided novel lightings on the diagnostic research of OP.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13018-021-02329-1.

Driver speed compliance following automatic incident detection: Insights from a naturalistic driving study

Automatic incident detection (AID) systems and variable speed limits (VSLs) can reduce crash probability and traffic congestion. Studies based on loop detector data have shown that AID systems decrease the variation in speeds between drivers. Despite the impact on driver behaviour characteristics, most mathematical models evaluating the effect of AID systems on traffic operations do not capture driver response realistically. This study examines the main factors related to driver speed compliance with a sequence of three VSLs triggered by an AID system. For this purpose, the variable speed limit database of the executive agency of the Dutch Ministry of Infrastructure and Water Management (Rijkswaterstaat) was integrated into the UDRIVE naturalistic driving database for passenger car data collected in the Netherlands. The video data were annotated to analyse driver glance behaviour and secondary task engagement. A logistic regression model was estimated to predict driver speed compliance after each VSL in the sequence. The results reveal that the factors predicting compliance to the VSLs differ based on which of the three VSLs the driver is subjected to. Low speeds and accelerations before the gantry, approaching a slower leader, high proportion of time with eyes-on-road and close consecutive gantries were associated with high compliance with the first VSL in the sequence (i.e., indicating a speed limit of 70 km/h with flashing attention lights). Low speeds and accelerations before the gantry, close consecutive gantries and a small number of lanes resulted in high compliance with the second VSL (i.e., a speed limit of 50 km/h with flashing attention lights). Low speeds before the gantry and close consecutive gantries were linked to high compliance with the third VSL (i.e., indicating a speed limit of 50 km/h). Although further investigations based on a larger sample are needed, these findings are relevant to the development of human-like driving assistance systems and of traffic simulations that assess the impact of AID systems on traffic operations realistically.

Assessing the likelihood of secondary crashes on freeways with Adaptive Signal Control System deployed on alternate routes

INTRODUCTION

Reducing the likelihood of freeway secondary crashes will provide significant safety, operational and environmental benefits. This paper presents a method for assessing the likelihood of freeway secondary crashes with Adaptive Signal Control Systems (ASCS) deployed on alternate routes that are typically used by diverted freeway traffic to avoid any delay or congestion due to a freeway primary crash.

METHOD

The method includes four steps: (1) identification of secondary crashes, (2) verification of alternate routes, (3) assessment of the likelihood of secondary crashes for freeways with ASCS deployed on alternate routes and non-ASCS (i.e. pre-timed, semi- or fully-actuated) alternate routes, and (4) investigation of unobserved heterogeneity of the likelihood of freeway secondary crashes. Four freeway sections (i.e., two with ASCS deployed on alternate routes and two non-ASCS alternate routes) in South Carolina are considered.

RESULTS AND CONCLUSIONS

Findings from the logistic regression modeling reveal significant reduction in the likelihood of secondary crashes for one freeway section (i.e., Charleston I-26 E) with ASCS deployed on alternate route. Other factors such as rear-end crash, dark or limited light, peak period, and annual average daily traffic contribute to the likelihood of freeway secondary crashes. Furthermore, random-parameter logistic regression model results for Charleston I-26 E reveal that unobserved heterogeneity of ASCS effect exists across the observations and ASCS are associated with the reduction of the likelihood of freeway secondary crashes for 84% of the observations (i.e., primary crashes). Location of the primary crash on the freeway is observed to affect the benefit of ASCS toward freeway secondary crash reduction as the primary crash's location determines how many upstream freeway vehicles will be able to take the alternate route. Practical Applications: Based on the findings, it is recommended that the South Carolina Department of Transportation (SCDOT) considers deploying ASCS on alternate routes parallel to freeway sections where high percentages of secondary crashes are found.

Identification of biomarkers associated with clinical severity of chronic obstructive pulmonary disease

We sought to identify the biomarkers related to the clinical severity of stage I to stage IV chronic obstructive pulmonary disease (COPD). Gene expression profiles from the blood samples of COPD patients at each of the four stages were acquired from the Gene Expression Omnibus Database (GEO, accession number: GSE54837). Genes showing expression changes among the different stages were sorted by soft clustering. We performed functional enrichment, protein-protein interaction (PPI), and miRNA regulatory network analyses for the differentially expressed genes. The biomarkers associated with the clinical classification of COPD were selected from logistic regression models and the relationships between TLR2 and inflammatory factors were verified in clinical blood samples by qPCR and ELISA. Gene clusters demonstrating continuously rising or falling changes in expression (clusters 1, 2, and 7 and clusters 5, 6, and 8, respectively) from stage I to IV were defined as upregulated and downregulated genes, respectively, and further analyzed. The upregulated genes were enriched in functions associated with defense, inflammatory, or immune responses. The downregulated genes were associated with lymphocyte activation and cell activation. TLR2, HMOX1, and CD79A were hub proteins in the integrated network of PPI and miRNA regulatory networks. TLR2 and CD79A were significantly correlated with clinical classifications. TLR2 was closely associated with inflammatory responses during COPD progression. Functions associated with inflammatory and immune responses as well as lymphocyte activation may play important roles in the progression of COPD from stage I to IV. TLR2 and CD79A may serve as potential biomarkers for the clinical severity of COPD. TLR2 and CD79A may also serve as independent biomarkers in the clinical classification in COPD. TLR2 may play an important role in the inflammatory responses of COPD.

Higher urinary nitrate was associated with lower prevalence of congestive heart failure: results from NHANES

Background

Some studies have reported that nitrate intake from vegetables was inversely associated with many vascular diseases, but few studies have paid attention to the relationship between urinary nitrate and cardiovascular diseases (CVDs). This cross-sectional study aimed to explore the connections between urinary nitrate and prevalence of CVDs.

Methods

The data of this study was collected from National Health and Nutrition Examination Survey (NHANES). Finally, several years’ data of NHANES were merged into 14,894 observations. Logistic regression models were used to examine the associations between urinary nitrate and CVDs by using the “survey” package in R software (version 3.2.3).

Results

In the univariable logistic analysis, significant association was discovered between urinary nitrate and congestive heart failure, coronary heart disease, angina pectoris, myocardial infarction (all P < 0.001). By adjusting related covariates, the multivariable logistic analysis showed that the significant association only existed between urinary nitrate and congestive heart failure (OR = 0.651, 95% CI 0.507–0.838, P < 0.001). Compared to Q1 urinary nitrate level as reference, the risk for prevalent heart failure diminished along with increasing levels of urinary nitrates, (OR of Q2 level = 0.633, 95% CI 0.403–0.994), (OR of Q3 level = 0.425, 95% CI 0.230–0.783), (OR of Q4 level = 0.375, 95% CI 0.210–0.661), respectively. Moreover, urinary nitrate levels were associated with congestive heart failure in a dose-dependent manner in both 20–60 years group, 60+ years group and male, female group (P < 0.001, P = 0.011 and P = 0.009, P = 0.004).

Conclusions

Independent of related covariates, higher urinary nitrate was associated with lower prevalent congestive heart failure.

Association between carotid intima media thickness and small dense low-density lipoprotein cholesterol in acute ischaemic stroke

BACKGROUND

Intima-media thickness (IMT) and small dense low-density lipoprotein cholesterol (sdLDL-C) have been reported to be related to atherosclerosis and stroke. This study is trying to explore the association between IMT and sdLDL-C in Chinese acute ischaemic stroke (AIS) subjects.

METHODS

This study enrolled total 368 consecutive AIS patients and 165 non-AIS controls from November 2016 to February 2019. Mean IMT and carotid plaques were measured by using carotid ultrasonography method. Blood glucose and lipid parameters were measured by using an automatic biochemical instrument. SdLDL-C was detected by using the Lipoprint LDL system. IMT > 1.0 mm was defined as increased IMT. Plaque stability based on the nature of the echo was determined by ultrasound examination. Risk factors for IMT were identified by using multivariate logistic regression analysis. A logistic regression model was established to predict AIS risk. Python software (Version 3.6) was used for the statistical analysis of all data.

RESULTS

The carotid IMT, proportion of plaques, and the sdLDL-C, triglycerides (TG) and glucose levels were obviously higher in AIS patients than those in controls. SdLDL-C level in the IMT thickening group was higher than that in the normal IMT group. SdLDL-C and total cholesterol (TC) were risk factors for IMT, while sdLDL-C was an independent risk factor. The IMT value of the unstable plaque group was markedly higher than that of the stable plaque group. The predictive value of IMT for AIS was better than that of low-density lipoprotein cholesterol (LDL-C) and non-high-density lipoprotein cholesterol (non-HDL-C) but not as good as that of sdLDL-C. A logistic regression model was established to predict AIS risk. Additionally, carotid IMT and sdLDL-C were closely related to AIS severity and outcomes.

CONCLUSIONS

SdLDL-C and TC were risk factors for increased IMT, while sdLDL-C was an independent risk factor. A prediction model based on IMT and other variables was established to screen the population with high AIS risk.

A mass spectrometry database for identification of saponins in plants

Saponins constitute an important class of secondary metabolites of the plant kingdom. Here, we present a mass spectrometry-based database for rapid and easy identification of saponins henceforth referred to as saponin mass spectrometry database (SMSD). With a total of 4196 saponins, 214 of which were obtained from commercial sources. Through liquid chromatography-tandem high-resolution/mass spectrometry (HR/MS) analysis under negative ion mode, the fragmentation behavior for all parent fragment ions almost conformed to successive losses of sugar moieties, α-dissociation and McLafferty rearrangement of aglycones in high-energy collision induced dissociation. The saccharide moieties produced sugar fragment ions from m/z (monosaccharide) to m/z (polysaccharides). The parent and sugar fragment ions of other saponins were predicted using the above mentioned fragmentation pattern. The SMSD is freely accessible at http://47.92.73.208:8082/ or http://cpu-smsd.com (preferrably using google). It provides three search modes ("CLASSIFY", "SEARCH" and "METABOLITE"). Under the "CLASSIFY" function, saponins are classified with high predictive accuracies from all metabolites by establishment of logistic regression model through their mass data from HR/MS input as a csv file, where the first column is ID and the second column is mass. For the "SEARCH" function, saponins are searched against parent ions with certain mass tolerance in "MS Ion Search". Then, daughter ions with certain mass tolerance are input into "MS/MS Ion Search". The optimal candidates were screened out according to the match count and match rate values in comparison with fragment data in database. Additionally, another logistic regression model completely differentiated between parent and sugar fragment ions. This function designed in front web is conducive to search and recheck. With the "METABOLITE" function, saponins are searched using their common names, where both full and partial name searches are supported. With these modes, saponins of diverse chemical composition can be explored, grouped and identified with a high degree of predictive accuracy. This specialized database would aid in the identification of saponins in complex matrices particular in the study of traditional Chinese medicines or plant metabolomics.

Epigenome-wide association study reveals CpG sites related to COG of neuroblastoma

Background. Neuroblastoma (NB) is the most common extracranial solid tumor in infants and children. Its variable location and complex pathogenesis make NB hard for early diagnosis and risk classification. Methodology. We analyzed the methylation data of 236 samples from patients with NB in Therapeutically Applicable Research to Generate Effective Treatments (TARGET) database. Kaplan–Meier survival analysis was used for comparing overall survival of NB patients in different groups. Epigenome-wide association study (EWAS) was conducted to screen CpGs significantly associated with NB patients’ Children’s Oncology Group (COG). Logistic regression method was used for constructing a model to predict NB patients’ COG. Results. NB patients in low COG showed significantly superior prognosis than those in high COG. A total of seven CpG sites were found closely related to COG. Logistic regression model based on those CpGs showed superior performance in separating NB patients in different COGs. Conclusions. The present study highlights the important role of DNA methylation in NB development, which might provide evidence for treatment decisions for children NB.

Relevance of sex, age and gait kinematics when predicting fall-risk and mortality in older adults

Approximately one-third of elderly people fall each year with severe consequences, including death. The aim of this study was to identify the most relevant features to be considered to maximize the accuracy of a logistic regression model designed for prediction of fall/mortality risk among older people. This study included 261 adults, aged over 65 years. Men and women were analyzed separately because sex stratification was revealed as being essential for our purposes of feature ranking and selection. Participants completed a 3-m walk test at their own gait velocity. An inertial sensor attached to their lumbar spine was used to record acceleration data in the three spatial directions. Signal processing techniques allowed the extraction of 21 features representative of gait kinematics, to be used as predictors to train and test the model. Age and gait speed data were also considered as predictors. A set of 23 features was considered. These features demonstrate to be more or less relevant depending on the sex of the cohort under analysis and the classification label (risk of falls and mortality). In each case, the minimum size subset of relevant features is provided to show the maximum accuracy prediction capability. Gait speed has been largely used as the single feature for the prediction fall risk among older adults. Nevertheless, prediction accuracy can be substantially improved, reaching 70% in some cases, if the task of training and testing the model takes into account some other features, namely, sex, age and gait kinematic parameters. Therefore we recommend considering sex, age and step regularity to predict fall-risk.

Predicting the risk of sarcopenia in elderly patients with patellar fracture: development and assessment of a new predictive nomogram

Purpose

To develop a risk prediction model for postoperative sarcopenia in elderly patients with patellar fractures in China.

Patients and methods

We conducted a community survey of patients aged ≥55 years who underwent surgery for patellar fractures between January 2013 and October 2018, through telephone interviews, community visits, and outpatient follow-up. We established a predictive model for assessing the risk of sarcopenia after patellar fractures. We developed the prediction model by combining multivariate logistic regression analysis with the least absolute shrinkage model and selection operator regression (lasso analysis) as well as the Support Vector Machine (SVM) algorithm. The predictive quality and clinical utility of the predictive model were determined using C-index, calibration plots, and decision curve analysis. We also conducted internal sampling methods for qualitative assessment.

Result

We recruited 137 participants (53 male; mean age, 65.7 years). Various risk factors were assessed, and low body mass index and advanced age were identified as the most important risk factor (P < 0.05). The prediction rate of the model was good (C-index: 0.88; 95% CI [0.80552–0.95448]), with a satisfactory correction effect. The C index is 0.97 in the validation queue and 0.894 in the entire cohort. Decision curve analysis suggested good clinical practicability.

Conclusion

Our prediction model shows promise as a cost-effective tool for predicting the risk of postoperative sarcopenia in elderly patients based on the following: advanced age, low body mass index, diabetes, less outdoor exercise, no postoperative rehabilitation, different surgical methods, diabetes, open fracture, and removal of internal fixation.

Early age at menarche and its associated factors in school girls (age, 10 to 12 years) in Bangladesh: a cross-section survey in Rajshahi District, Bangladesh

Background

Early onset of menarche is one of the most important factors for breast cancer and other associated health hazards. The aim of this study was to investigate the early age at menarche and its associated factors in school girls (age, 10–12 years) in Rajshahi District, Bangladesh.

Methods

Data was collected from Rajshahi District, Bangladesh, using multistage random sampling. Independent sample t test and binary logistic regression model were used in this study. A total number of 386 school girls aged 10–12 years were considered as a sample for this study.

Results

This study revealed that more than 48% girls already attained menarche within the age of 12 years, among them 25.6%, 41.0%, and 58.3% girls experienced menarche at the age of 10, 11, and 12 years, respectively. It was observed that the menarcheal girls were significantly taller (p < 0.01) and heavier (p < 0.01) than non-menarcheal girls. The menarcheal girls’ mothers were heavier (p < 0.01), shorter (p < 0.01), had more BMI (p < 0.01), reached menarche (p < 0.05) earlier than non-menarcheal girls’ mothers. Menarcheal girls had less number of siblings (p < 0.01) and lower order of birth (p < 0.05) than non-menarcheal girls. After controlling the effect of other factors, multiple logistic regression model demonstrated that obese girls were more likely to attain menarche than under- [AOR = 0.279, CI 95% 0.075–0.986; p < 0.05] and normal [AOR = 0.248, CI 95% 0.082–0.755; p < 0.05] weight girls. Urban school girls had more chance to get menarche than rural school girls at same age (AOR = 0.012, 95% CI 0.003–0.047; p < 0.01).

Conclusions

Therefore, modern lifestyle changes may have the important factors for early age at menarche of the studied girls in Bangladesh.

Association of Small Dense Low-Density Lipoprotein Cholesterol with Stroke Risk, Severity and Prognosis

Aim: To investigate the association of small dense low-density lipoprotein cholesterol (sdLDL-C) and acute ischemic stroke (AIS) in terms of risk, severity, and outcomes. Prediction models were established to screen high-risk patients and predict prognosis of AIS patients.

Methods: We enrolled in this study 355 AIS patients and 171 non-AIS controls. AIS was subtyped according to TOAST criteria, and the severity and outcomes of AIS were measured. Blood glucose and lipid profiles including total cholesterol, triglyceride, and lipoproteins were measured in all patients using automatic measure. Lipoprotein subfractions were detected by the Lipoprint LDL system.

Results: As compared with the non-AIS control group, the AIS group had higher sdLDL-C levels. Pearson correlation analysis revealed that the sdLDL-C level and risk of AIS, especially non-cardioembolic stroke, were positively correlated. The area under the curve of sdLDL-C for AIS risk was 0.665, better than that of other lipids. Additionally, the sdLDL-C level was significantly correlated with AIS severity and bad outcomes. A logistic regression model for assessing the probability of AIS occurrence and a prognostic prediction model were established based on sdLDL-C and other variables.

Conclusions: Elevated levels of sdLDL-C were associated with a higher prevalence of AIS, especially in non-cardioembolic stroke subtypes. After adjustment for other risk factors, sdLDL-C was found to be an independent risk factor for AIS. Also, sdLDL-C level was strongly associated with AIS severity and poor functional outcomes. Logistic regression models for AIS risk and prognosis prediction were established to help clinicians provide better prevention for high-risk subjects and monitor their prognosis.